Artificial Intelligence
Sponsored by
Sponsored logo

Scholar

 Scholar
Ask a question and accept an answer.
Awarded 1614 times.
Understanding multi-iteration updates of the model in the Proximal Policy Optimization algorithm
Awarded 2 days ago
What is $ \nabla_{\theta_{k-1}} \theta_{k}$ in the context of MAML?
Awarded 2 days ago
Comparing a large/general CNN to a smaller more specialized one?
Awarded Jan 9 at 22:18
What are support values in a support vector machine?
Awarded Jan 9 at 12:50
Have I understood the loss function from the original U-Net paper correctly?
Awarded Jan 8 at 13:05
In OCR, how should I deal with the warped text on the sides of oval objects?
Awarded Jan 7 at 21:20
Training a classifier on different datasets with different image conditions for different labels causes the model to infer using the background
Awarded Jan 7 at 16:22
How should I generate datasets for a SARSA agent when the environment is not simple?
Awarded Jan 6 at 10:16
How to express a fully connected neural network succintly using linear algebra?
Awarded Jan 6 at 8:17
Can TensorFlow, PyTorch, and other mainstream ML frameworks be used for research-grade work in AI?
Awarded Jan 6 at 0:19
Defining an action space for card games like Magic: the Gathering
Awarded Jan 5 at 19:46
In CNNs, why do we sum the filter derivatives w.r.t the loss function to get the final gradient?
Awarded Jan 5 at 10:12
Using DDPG for control in multi-dimensional continuous action space?
Awarded Jan 4 at 14:26
How to design a NLP algorithm to find a food item in menu card list?
Awarded Jan 4 at 4:40
Transformers: How to use the target mask properly?
Awarded Jan 3 at 22:51
How is the latent vector transforming to a feature map in DCGAN (Generator structure)?
Awarded Jan 2 at 17:52
When updating the state-action value in the Monte Carlo method, is the return the same for each state-action pair?
Awarded Jan 2 at 9:41
What is emperical distribution in MLE?
Awarded Jan 2 at 5:40
Is it possible to integrate the GPT-3 by OpenAPI inside Unity3D or any game-engine?
Awarded Jan 1 at 12:20
Output volume proof for convolutional neural network
Awarded Dec 31 '20 at 16:35
How are these equations of SGD with momentum equivalent?
Awarded Dec 31 '20 at 8:05
Can you use machine learning for binary data?
Awarded Dec 29 '20 at 12:25
Regression For Elliptical Curve Public Key Generation Possible?
Awarded Dec 28 '20 at 22:03
Unclear definition of a “leaf” and diverging UTC values in the Monte Carlo Tree Search
Awarded Dec 28 '20 at 18:37
How can I do video classification while taking into account the temporal dependencies of the frames?
Awarded Dec 28 '20 at 17:15
RL: Encoding action conditioned on previous action
Awarded Dec 28 '20 at 5:40
What is a unified neural network model?
Awarded Dec 27 '20 at 22:27
Loss randomly changing, incorrect output (even for low loss) when trying to overfit on a single set of input and output
Awarded Dec 27 '20 at 7:45
How to derive matrix form of the Bellman operators?
Awarded Dec 26 '20 at 15:17
What ensemble methods are used in the state-of-the-art models?
Awarded Dec 25 '20 at 2:08
How do I select the (number of) negative cases, if I'm given a set of positive cases?
Awarded Dec 21 '20 at 16:31
Can a convolutional neural network classify text document images?
Awarded Dec 21 '20 at 13:03
AI, Machine learning prediction algorithms which can predict maximum lifespan of Human being in future centuries [closed]
Awarded Dec 21 '20 at 2:40
Are there any good alternatives to an LSTM language model for text generation?
Awarded Dec 18 '20 at 22:33
Is there a proof to explain why XOR cannot be linearly separable?
Awarded Dec 17 '20 at 9:21
In the multi-head attention mechanism of the transformer, why do we need both $W_i^Q$ and ${W_i^K}^T$?
Awarded Dec 17 '20 at 5:36
What does “class-level discriminative feature representation” mean in the paper “Semi-Supervised Deep Learning with Memory”?
Awarded Dec 17 '20 at 5:31
In attention models with multiple layers, are weight matrices shared across layers?
Awarded Dec 17 '20 at 2:19
Does the image is logistic regression or SVM, and why? [closed]
Awarded Dec 16 '20 at 22:15
Which classifier should I use for a dataset with one feature?
Awarded Dec 16 '20 at 16:51
In AlphaZero, do we need to store the data of terminal states?
Awarded Dec 16 '20 at 16:36
Equivalence of the $Q(s,a)$ and $V(s)$ under optimality conditions?
Awarded Dec 15 '20 at 12:28
Can someone explain me what does this loss curve says?
Awarded Dec 15 '20 at 9:58
Why does my neural network to predict $x$ given $\sin(x)$ not generalize?
Awarded Dec 14 '20 at 13:07
How are continuous actions sampled (or generated) from the policy network in PPO?
Awarded Dec 13 '20 at 13:31
What is different in each head of a multi-head attention mechanism?
Awarded Dec 13 '20 at 0:37
Can we use transformers for audio classification tasks?
Awarded Dec 11 '20 at 16:20
How is the DQN loss derived from (or theoretically motivated by) the Bellman equation, and how is it related to the Q-learning update?
Awarded Dec 10 '20 at 16:07
Is there a taxonomy of adversarial attacks?
Awarded Dec 10 '20 at 12:11
Why is my implementation of Q-learning not converging to the right values in the FrozenLake environment?
Awarded Dec 9 '20 at 0:04
Why would the learning rate curve go backwards?
Awarded Dec 8 '20 at 6:12
AlphaGo Zero: does $Q(s_t, a)$ dominate $U(s_t, a)$ in difficult game states?
Awarded Dec 6 '20 at 7:11
What is the impact of the number of features on the prediction power of a neural network?
Awarded Dec 5 '20 at 14:33
Why does each component of the tuple that represents an action have a categorical distribution in the TRPO paper?
Awarded Dec 3 '20 at 17:07
A mathematical explanation of Attention Mechanism
Awarded Dec 3 '20 at 2:45
Mining repeated subsequences in a given sequence
Awarded Dec 2 '20 at 22:43
What happens when the agent faces a state that never before encountered?
Awarded Dec 2 '20 at 13:56
Autoencoder: predictions missing for nodes in the bottleneck layer
Awarded Dec 1 '20 at 11:45
What constitutes a large space state (in Q-learning)?
Awarded Nov 29 '20 at 17:28
Does this diagram represent several LSTMs, or one through several timesteps?
Awarded Nov 27 '20 at 13:22
1
2 3 4 5
…
27